© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    5. GPT2-Small
    7. Residual Stream
    9. 2-RES-JB
    11. 1874
    Prev
    Next
    INDEX
    Explanations

    dates in a specific format (e.g., month, day, year) within the text

    oai_token-act-pair · gpt-3.5-turbo

    dates and specific years mentioned in the text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 2-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.hook_resid_pre
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    24,576
    Data Type
    torch.float32
    Hook Point
    blocks.2.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    2
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    iaries
    -0.77
    awed
    -0.73
    imated
    -0.73
    upp
    -0.72
    ongh
    -0.70
    elong
    -0.69
     unch
    -0.69
    earable
    -0.68
     tremend
    -0.68
    vil
    -0.67
    POSITIVE LOGITS
     partName
    0.94
    ]]
    0.87
     RELEASE
    0.83
    âĶĢâĶĢâĶĢâĶĢ
    0.82
    DragonMagazine
    0.79
     GMT
    0.77
    ]),
    0.75
    20439
    0.74
    å¹
    0.73
    ---
    0.72
    Activations Density 0.125%

    No Known Activations